A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM
The vibration signal of rolling bearings is a nonlinear and non-stationary signal, which is affected by the working condition change and background noise, and the reliability of traditional feature extraction methods and fault identification methods is low. In order to effectively extract feature ve...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10283816/ |
| _version_ | 1797655686059917312 |
|---|---|
| author | Rongrong Lu Miao Xu Chengjiang Zhou Zhaodong Zhang Shanyou He Qihua Yang Min Mao Jingzong Yang |
| author_facet | Rongrong Lu Miao Xu Chengjiang Zhou Zhaodong Zhang Shanyou He Qihua Yang Min Mao Jingzong Yang |
| author_sort | Rongrong Lu |
| collection | DOAJ |
| description | The vibration signal of rolling bearings is a nonlinear and non-stationary signal, which is affected by the working condition change and background noise, and the reliability of traditional feature extraction methods and fault identification methods is low. In order to effectively extract feature vectors and improve the accuracy and reliability of fault identification, we propose a new fault diagnosis method based on noise eliminated ensemble empirical mode decomposition and robust unsupervised feature selection with local preservation (NEEEMD-RUSLP) and binary tree least squares twin support vector machine (BTLSTSVM). Firstly, NEEEMD is introduced to suppress background noise and decompose the vibration signal into a series of intrinsic mode functions (IMF), and the wavelet packet energy entropy, packet energy coefficient, and Gini coefficient of each IMF are extracted to construct time-frequency domain features. Then, 16 time-domain features and 13 frequency-domain features of the original signal are extracted and combined with the time-frequency domain features of each IMF to construct a high-dimensional feature space. In order to reduce the feature dimension and improve the diagnostic accuracy of the model, the RUSLP feature selection method is introduced to select effective low-dimensional features from the high-dimensional features. In addition, the binary tree (BT) strategy is introduced into the LSTSVM binary classifier to construct the BTLSTSVM multi-classifier, which aims to improve the recognition accuracy of low-dimensional features. In the bearing fault diagnosis of Case Western Reserve University, the fault diagnosis accuracy obtained by the proposed method is improved by 10.67%. In the bearing fault diagnosis of the University of Ottawa, the fault diagnosis accuracy obtained by the proposed method is improved by 10%. In the fault diagnosis of check valve in the actual industrial production environment, the fault diagnosis accuracy obtained by the proposed method is improved by 22%. The results show that the proposed method can not only effectively extract and select the low-dimensional fault characteristics of the bearing, but also achieve competitive fault diagnosis accuracy. Therefore, this method can provide a new method reference for the field of fault diagnosis, and has great theoretical significance and application value. |
| first_indexed | 2024-03-11T17:18:10Z |
| format | Article |
| id | doaj.art-ff28bb28927a436f924e5d4ae844a033 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T17:18:10Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ff28bb28927a436f924e5d4ae844a0332023-10-19T23:01:20ZengIEEEIEEE Access2169-35362023-01-011111396511399410.1109/ACCESS.2023.332405410283816A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVMRongrong Lu0https://orcid.org/0009-0001-6864-3016Miao Xu1https://orcid.org/0009-0006-1149-2575Chengjiang Zhou2https://orcid.org/0000-0003-4218-105XZhaodong Zhang3Shanyou He4Qihua Yang5https://orcid.org/0000-0001-7895-3483Min Mao6https://orcid.org/0000-0002-0209-4077Jingzong Yang7https://orcid.org/0000-0002-2211-8718School of Information Science and Technology, Yunnan Normal University, Kunming, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming, ChinaFaculty of Information Engineering, Quzhou College of Technology, Quzhou, ChinaSchool of Big Data, Baoshan University, Baoshan, Yunnan, ChinaThe vibration signal of rolling bearings is a nonlinear and non-stationary signal, which is affected by the working condition change and background noise, and the reliability of traditional feature extraction methods and fault identification methods is low. In order to effectively extract feature vectors and improve the accuracy and reliability of fault identification, we propose a new fault diagnosis method based on noise eliminated ensemble empirical mode decomposition and robust unsupervised feature selection with local preservation (NEEEMD-RUSLP) and binary tree least squares twin support vector machine (BTLSTSVM). Firstly, NEEEMD is introduced to suppress background noise and decompose the vibration signal into a series of intrinsic mode functions (IMF), and the wavelet packet energy entropy, packet energy coefficient, and Gini coefficient of each IMF are extracted to construct time-frequency domain features. Then, 16 time-domain features and 13 frequency-domain features of the original signal are extracted and combined with the time-frequency domain features of each IMF to construct a high-dimensional feature space. In order to reduce the feature dimension and improve the diagnostic accuracy of the model, the RUSLP feature selection method is introduced to select effective low-dimensional features from the high-dimensional features. In addition, the binary tree (BT) strategy is introduced into the LSTSVM binary classifier to construct the BTLSTSVM multi-classifier, which aims to improve the recognition accuracy of low-dimensional features. In the bearing fault diagnosis of Case Western Reserve University, the fault diagnosis accuracy obtained by the proposed method is improved by 10.67%. In the bearing fault diagnosis of the University of Ottawa, the fault diagnosis accuracy obtained by the proposed method is improved by 10%. In the fault diagnosis of check valve in the actual industrial production environment, the fault diagnosis accuracy obtained by the proposed method is improved by 22%. The results show that the proposed method can not only effectively extract and select the low-dimensional fault characteristics of the bearing, but also achieve competitive fault diagnosis accuracy. Therefore, this method can provide a new method reference for the field of fault diagnosis, and has great theoretical significance and application value.https://ieeexplore.ieee.org/document/10283816/Empirical mode decompositionunsupervised feature selectionmixed domainfault diagnosisleast square twin support vector machine |
| spellingShingle | Rongrong Lu Miao Xu Chengjiang Zhou Zhaodong Zhang Shanyou He Qihua Yang Min Mao Jingzong Yang A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM IEEE Access Empirical mode decomposition unsupervised feature selection mixed domain fault diagnosis least square twin support vector machine |
| title | A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM |
| title_full | A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM |
| title_fullStr | A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM |
| title_full_unstemmed | A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM |
| title_short | A Novel Fault Diagnosis Method Based on NEEEMD-RUSLP Feature Selection and BTLSTSVM |
| title_sort | novel fault diagnosis method based on neeemd ruslp feature selection and btlstsvm |
| topic | Empirical mode decomposition unsupervised feature selection mixed domain fault diagnosis least square twin support vector machine |
| url | https://ieeexplore.ieee.org/document/10283816/ |
| work_keys_str_mv | AT rongronglu anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT miaoxu anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT chengjiangzhou anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT zhaodongzhang anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT shanyouhe anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT qihuayang anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT minmao anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT jingzongyang anovelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT rongronglu novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT miaoxu novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT chengjiangzhou novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT zhaodongzhang novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT shanyouhe novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT qihuayang novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT minmao novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm AT jingzongyang novelfaultdiagnosismethodbasedonneeemdruslpfeatureselectionandbtlstsvm |